© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18795
    Prev
    Next
    INDEX
    Explanations

    manufacturing-related terms and topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.7%
    496
    +0.13
    0.6%
    459
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.14
    0.02
    288
    +0.13
    0.02
    459
    +0.13
    0.02
    Negative Logits
    mins
    -0.78
    tein
    -0.69
    pan
    -0.68
    retion
    -0.67
    mire
    -0.65
    orr
    -0.64
    agher
    -0.64
    wick
    -0.64
    ander
    -0.63
    visor
    -0.63
    POSITIVE LOGITS
     Consent
    0.93
     manufacturing
    0.91
     manufactures
    0.88
     goods
    0.85
    eers
    0.81
     defect
    0.77
     warranties
    0.76
     packaging
    0.76
     Manufacturing
    0.75
     defects
    0.75
    Activations Density 0.042%

    No Known Activations